Model results

LiveBench

Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.

Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.

Reviewed recommendation and limits

Use LiveBench V2 as a suite-level complement to AA Intelligence Index for a general-purpose shortlist. Start with its Browser Use or Agentic suite for screenshot interaction or persistent app work. Choose Reasoning for ground-truth answer checks.

V1 and V2 2026-10-14 stay separate. V2 equally averages measured suites and uses one run at supported effort. Grading mixes answer checks, tests, application outcomes and rubrics. Imported groups below may use different protocols; this review does not certify each run. Single runs and averages over different measured suites limit overall comparisons. Research uses rubrics and Design uses visual and structural grading; grader validation is not disclosed. V1 contamination claims do not certify V2. Measurement dates are not reported.

Publisher results LiveBench methodology

← All evaluation groups

LiveBench overall

Source: LiveBench
Version: v1
Measurement date: 2025-05-30
Metric: % · Higher is better
Evaluation scope: Mean across that public release's task columns

Exact score ties share a position. Positions do not establish statistical significance. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.

#1GPT-5 Codex
openai/gpt-5-codex
79.6%
View modelEvidence independent
#2GPT-5
openai/gpt-5-2025-08-07
75.6%
View modelEvidence independent
#3DeepSeek V3.1 Terminus
deepseek/deepseek-v3.1-terminus
71.9%
View modelEvidence independent
#4GLM 4.5
z-ai/glm-4.5
65.9%
View modelEvidence independent
#5MiniMax M2
minimax/minimax-m2
65.3%
View modelEvidence independent
#6GLM 4.5 Air
z-ai/glm-4.5-air
61.2%
View modelEvidence independent
#7Mistral Medium 3
mistralai/mistral-medium-3
50.2%
View modelEvidence independent
#7Mistral Medium 3.1
mistralai/mistral-medium-3.1
50.2%
View modelEvidence independent
#7Mistral Medium 3.5
mistralai/mistral-medium-3.5-20260430
50.2%
View modelEvidence independent